Effective prediction and its computational complexity

Authors:
Richard Taylor
Affiliations:
Australian Defence Science and Technology Organisation, Fern Hill Park ACT, Australia
Venue:
CATS '07 Proceedings of the thirteenth Australasian symposium on Theory of computing - Volume 65
Year:
2007

Citing 5
Cited 0

Randomness conservation inequalities; information and independence in mathematical theories

Information and Control
Analysis and design of stream ciphers

Analysis and design of stream ciphers
An introduction to Kolmogorov complexity and its applications (2nd ed.)

An introduction to Kolmogorov complexity and its applications (2nd ed.)
Computers and Intractability: A Guide to the Theory of NP-Completeness

Computers and Intractability: A Guide to the Theory of NP-Completeness
Learning Quickly When Irrelevant Attributes Abound: A New Linear-Threshold Algorithm

Machine Learning

Quantified Score

Hi-index	0.00

Visualization

Abstract

A model for the problem of predicting the outputs of a process, based only on knowledge of previous outputs, is proposed in terms of a decision problem. The strength of this particular formulation of the decision problem follows from the accuracy of its outputs in predicting the outputs of any particular deterministic process, and this predictability is quantified in terms of the number of bits the process may generate, and its length/time complexity. Both upper and lower bounds on the computational complexity of this decision problem are provided